21501721037

Committed 30 Jan 2026 02:00AM UTC coverage: 91.159% (-1.3%) from 92.426%

Build Type

push

github

Committed by

Commit Message

wip

Run Details

2681 of 2941 relevant lines covered (91.16%)

0.91 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

95.18

/src/Texy/Modules/LongWordsModule.php

<?php

/**
 * This file is part of the Texy! (https://texy.nette.org)
 * Copyright (c) 2004 David Grudl (https://davidgrudl.com)
 */

declare(strict_types=1);

namespace Texy\Modules;

use Texy;
use Texy\Syntax;
use function array_flip, array_pop, array_splice, count, end, iconv_strlen, implode, ord;


/**
 * Breaks long words with soft hyphens for better line wrapping.
 */
final class LongWordsModule extends Texy\Module
{
        private const
                Dont = 0, // don't hyphenate
                Here = 1, // hyphenate here
                After = 2; // hyphenate after

        private const SafeLimit = 1000;

        public int $wordLimit = 20;

        /** @var array<string, int>|string[] */
        private array $consonants = [
                'b', 'c', 'd', 'f', 'g', 'h', 'j', 'k', 'l', 'm', 'n', 'p', 'q', 'r', 's', 't', 'v', 'w', 'x', 'z',
                'B', 'C', 'D', 'F', 'G', 'H', 'J', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'V', 'W', 'X', 'Z',
                "\u{10D}", "\u{10F}", "\u{148}", "\u{159}", "\u{161}", "\u{165}", "\u{17E}", // Czech UTF-8
                "\u{10C}", "\u{10E}", "\u{147}", "\u{158}", "\u{160}", "\u{164}", "\u{17D}",
        ];

        /** @var array<string, int>|string[] */
        private array $vowels = [
                'a', 'e', 'i', 'o', 'u', 'y',
                'A', 'E', 'I', 'O', 'U', 'Y',
                "\u{E1}", "\u{E9}", "\u{11B}", "\u{ED}", "\u{F3}", "\u{FA}", "\u{16F}", "\u{FD}", // Czech UTF-8
                "\u{C1}", "\u{C9}", "\u{11A}", "\u{CD}", "\u{D3}", "\u{DA}", "\u{16E}", "\u{DD}",
        ];

        /** @var array<string, int>|string[] */
        private array $before_r = [
                'b', 'B', 'c', 'C', 'd', 'D', 'f', 'F', 'g', 'G', 'k', 'K', 'p', 'P', 'r', 'R', 't', 'T', 'v', 'V',
                "\u{10D}", "\u{10C}", "\u{10F}", "\u{10E}", "\u{159}", "\u{158}", "\u{165}", "\u{164}", // Czech UTF-8
        ];

        /** @var array<string, int>|string[] */
        private array $before_l = [
                'b', 'B', 'c', 'C', 'd', 'D', 'f', 'F', 'g', 'G', 'k', 'K', 'l', 'L', 'p', 'P', 't', 'T', 'v', 'V',
                "\u{10D}", "\u{10C}", "\u{10F}", "\u{10E}", "\u{165}", "\u{164}", // Czech UTF-8
        ];

        /** @var array<string, int>|string[] */
        private array $before_h = ['c', 'C', 's', 'S'];

        /** @var array<string, int>|string[] */
        private array $doubleVowels = ['a', 'A', 'o', 'O'];


        public function __construct(Texy\Texy $texy)
        {
                $this->consonants = array_flip($this->consonants);
                $this->vowels = array_flip($this->vowels);
                $this->before_r = array_flip($this->before_r);
                $this->before_l = array_flip($this->before_l);
                $this->before_h = array_flip($this->before_h);
                $this->doubleVowels = array_flip($this->doubleVowels);

                $texy->registerPostLine($this->postLine(...), Syntax::Hyphenation);
        }


        public function postLine(string $text): string
        {
                return Texy\Regexp::replace(
                        $text,
                        '~[^ \n\t\x14\x15\x16\x{2013}\x{2014}\x{ad}-]{' . $this->wordLimit . ',}~',
                        $this->pattern(...),
                );
        }


        /**
         * Parses long words.
         * @param  array<?string>  $matches
         */
        private function pattern(array $matches): string
        {
                [$mWord] = $matches;
                // [0] => lllloooonnnnggggwwwoorrdddd

                if (iconv_strlen($mWord, 'UTF-8') > self::SafeLimit) {
                        return $mWord;
                }

                $chars = Texy\Regexp::matchAll(
                        $mWord,
                        '~[' . Texy\Patterns::MARK . ']+|.~',
                );

                $chars = array_column($chars, 0);
                if (count($chars) < $this->wordLimit) {
                        return $mWord;
                }

                $s = [''];
                $trans = [-1];
                foreach ($chars as $key => $char) {
                        if (ord($char[0]) < 32) {
                                continue;
                        }

                        $s[] = $char;
                        $trans[] = $key;
                }

                $s[] = '';
                $len = count($s) - 2;

                $positions = [];
                $a = 0;
                $last = 1;

                while (++$a < $len) {
                        if ($s[$a] === "\u{A0}") {
                                $a++;
                                continue;  // here and after never
                        }

                        $hyphen = $this->getHyphen($s[$a], $s[$a - 1], $s[$a + 1]);

                        if ($hyphen === self::Dont && ($a - $last > $this->wordLimit * 0.6)) {
                                $positions[] = $last = $a - 1; // Hyphenate here
                        }

                        if ($hyphen === self::Here) {
                                $positions[] = $last = $a - 1; // Hyphenate here
                        }

                        if ($hyphen === self::After) {
                                $positions[] = $last = $a;
                                $a++; // Hyphenate after
                        }
                }

                $a = end($positions);
                if (($a === $len - 1) && isset($this->consonants[$s[$len]])) {
                        array_pop($positions);
                }

                $syllables = [];
                $last = 0;
                foreach ($positions as $pos) {
                        if ($pos - $last > $this->wordLimit * 0.6) {
                                $syllables[] = implode('', array_splice($chars, 0, $trans[$pos] - $trans[$last]));
                                $last = $pos;
                        }
                }

                $syllables[] = implode('', $chars);
                return implode("\u{AD}", $syllables);
        }


        private function getHyphen(string $ch, string $prev, string $next): int
        {
                if ($ch === '.') {
                        return self::Here;

                } elseif (isset($this->consonants[$ch])) { // consonants
                        if (isset($this->vowels[$next])) {
                                return isset($this->vowels[$prev]) ? self::Here : self::Dont;

                        } elseif (($ch === 's') && ($prev === 'n') && isset($this->consonants[$next])) {
                                return self::After;

                        } elseif (isset($this->consonants[$next], $this->vowels[$prev])) {
                                if ($next === 'r') {
                                        return isset($this->before_r[$ch]) ? self::Here : self::After;

                                } elseif ($next === 'l') {
                                        return isset($this->before_l[$ch]) ? self::Here : self::After;

                                } elseif ($next === 'h') { // CH
                                        return isset($this->before_h[$ch])
                                                ? self::Dont
                                                : self::After;
                                }

                                return self::After;
                        }

                        return self::Dont;

                } elseif (($ch === 'u') && isset($this->doubleVowels[$prev])) {
                        return self::After;

                } elseif (isset($this->vowels[$ch], $this->vowels[$prev])) {
                        return self::Here;
                }

                return self::Dont; // Do not hyphenate
        }
}

1	<?php
2
3	/**
4	* This file is part of the Texy! (https://texy.nette.org)
5	* Copyright (c) 2004 David Grudl (https://davidgrudl.com)
6	*/
7
8	declare(strict_types=1);
9
10	namespace Texy\Modules;
11
12	use Texy;
13	use Texy\Syntax;
14	use function array_flip, array_pop, array_splice, count, end, iconv_strlen, implode, ord;
15
16
17	/**
18	* Breaks long words with soft hyphens for better line wrapping.
19	*/
20	final class LongWordsModule extends Texy\Module
21	{
22	private const
23	Dont = 0, // don't hyphenate
24	Here = 1, // hyphenate here
25	After = 2; // hyphenate after
26
27	private const SafeLimit = 1000;
28
29	public int $wordLimit = 20;
30
31	/** @var array<string, int>\|string[] */
32	private array $consonants = [
33	'b', 'c', 'd', 'f', 'g', 'h', 'j', 'k', 'l', 'm', 'n', 'p', 'q', 'r', 's', 't', 'v', 'w', 'x', 'z',
34	'B', 'C', 'D', 'F', 'G', 'H', 'J', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'V', 'W', 'X', 'Z',
35	"\u{10D}", "\u{10F}", "\u{148}", "\u{159}", "\u{161}", "\u{165}", "\u{17E}", // Czech UTF-8
36	"\u{10C}", "\u{10E}", "\u{147}", "\u{158}", "\u{160}", "\u{164}", "\u{17D}",
37	];
38
39	/** @var array<string, int>\|string[] */
40	private array $vowels = [
41	'a', 'e', 'i', 'o', 'u', 'y',
42	'A', 'E', 'I', 'O', 'U', 'Y',
43	"\u{E1}", "\u{E9}", "\u{11B}", "\u{ED}", "\u{F3}", "\u{FA}", "\u{16F}", "\u{FD}", // Czech UTF-8
44	"\u{C1}", "\u{C9}", "\u{11A}", "\u{CD}", "\u{D3}", "\u{DA}", "\u{16E}", "\u{DD}",
45	];
46
47	/** @var array<string, int>\|string[] */
48	private array $before_r = [
49	'b', 'B', 'c', 'C', 'd', 'D', 'f', 'F', 'g', 'G', 'k', 'K', 'p', 'P', 'r', 'R', 't', 'T', 'v', 'V',
50	"\u{10D}", "\u{10C}", "\u{10F}", "\u{10E}", "\u{159}", "\u{158}", "\u{165}", "\u{164}", // Czech UTF-8
51	];
52
53	/** @var array<string, int>\|string[] */
54	private array $before_l = [
55	'b', 'B', 'c', 'C', 'd', 'D', 'f', 'F', 'g', 'G', 'k', 'K', 'l', 'L', 'p', 'P', 't', 'T', 'v', 'V',
56	"\u{10D}", "\u{10C}", "\u{10F}", "\u{10E}", "\u{165}", "\u{164}", // Czech UTF-8
57	];
58
59	/** @var array<string, int>\|string[] */
60	private array $before_h = ['c', 'C', 's', 'S'];
61
62	/** @var array<string, int>\|string[] */
63	private array $doubleVowels = ['a', 'A', 'o', 'O'];
64
65
66	public function __construct(Texy\Texy $texy)	1✔
67	{
68	$this->consonants = array_flip($this->consonants);	1✔
69	$this->vowels = array_flip($this->vowels);	1✔
70	$this->before_r = array_flip($this->before_r);	1✔
71	$this->before_l = array_flip($this->before_l);	1✔
72	$this->before_h = array_flip($this->before_h);	1✔
73	$this->doubleVowels = array_flip($this->doubleVowels);	1✔
74
75	$texy->registerPostLine($this->postLine(...), Syntax::Hyphenation);	1✔
76	}	1✔
77
78
79	public function postLine(string $text): string	1✔
80	{
81	return Texy\Regexp::replace(	1✔
82	$text,	1✔
83	'~[^ \n\t\x14\x15\x16\x{2013}\x{2014}\x{ad}-]{' . $this->wordLimit . ',}~',	1✔
84	$this->pattern(...),	1✔
85	);
86	}
87
88
89	/**
90	* Parses long words.
91	* @param array<?string> $matches
92	*/
93	private function pattern(array $matches): string	1✔
94	{
95	[$mWord] = $matches;	1✔
96	// [0] => lllloooonnnnggggwwwoorrdddd
97
98	if (iconv_strlen($mWord, 'UTF-8') > self::SafeLimit) {	1✔
99	return $mWord;	1✔
100	}
101
102	$chars = Texy\Regexp::matchAll(	1✔
103	$mWord,	1✔
104	'~[' . Texy\Patterns::MARK . ']+\|.~',	1✔
105	);
106
107	$chars = array_column($chars, 0);	1✔
108	if (count($chars) < $this->wordLimit) {	1✔
109	return $mWord;	1✔
110	}
111
112	$s = [''];	1✔
113	$trans = [-1];	1✔
114	foreach ($chars as $key => $char) {	1✔
115	if (ord($char[0]) < 32) {	1✔
116	continue;	1✔
117	}
118
119	$s[] = $char;	1✔
120	$trans[] = $key;	1✔
121	}
122
123	$s[] = '';	1✔
124	$len = count($s) - 2;	1✔
125
126	$positions = [];	1✔
127	$a = 0;	1✔
128	$last = 1;	1✔
129
130	while (++$a < $len) {	1✔
131	if ($s[$a] === "\u{A0}") {	1✔
132	$a++;	×
133	continue; // here and after never	×
134	}
135
136	$hyphen = $this->getHyphen($s[$a], $s[$a - 1], $s[$a + 1]);	1✔
137
138	if ($hyphen === self::Dont && ($a - $last > $this->wordLimit * 0.6)) {	1✔
139	$positions[] = $last = $a - 1; // Hyphenate here	1✔
140	}
141
142	if ($hyphen === self::Here) {	1✔
143	$positions[] = $last = $a - 1; // Hyphenate here	1✔
144	}
145
146	if ($hyphen === self::After) {	1✔
147	$positions[] = $last = $a;	1✔
148	$a++; // Hyphenate after	1✔
149	}
150	}
151
152	$a = end($positions);	1✔
153	if (($a === $len - 1) && isset($this->consonants[$s[$len]])) {	1✔
154	array_pop($positions);	1✔
155	}
156
157	$syllables = [];	1✔
158	$last = 0;	1✔
159	foreach ($positions as $pos) {	1✔
160	if ($pos - $last > $this->wordLimit * 0.6) {	1✔
161	$syllables[] = implode('', array_splice($chars, 0, $trans[$pos] - $trans[$last]));	1✔
162	$last = $pos;	1✔
163	}
164	}
165
166	$syllables[] = implode('', $chars);	1✔
167	return implode("\u{AD}", $syllables);	1✔
168	}
169
170
171	private function getHyphen(string $ch, string $prev, string $next): int	1✔
172	{
173	if ($ch === '.') {	1✔
174	return self::Here;	1✔
175
176	} elseif (isset($this->consonants[$ch])) { // consonants	1✔
177	if (isset($this->vowels[$next])) {	1✔
178	return isset($this->vowels[$prev]) ? self::Here : self::Dont;	1✔
179
180	} elseif (($ch === 's') && ($prev === 'n') && isset($this->consonants[$next])) {	1✔
181	return self::After;	×
182
183	} elseif (isset($this->consonants[$next], $this->vowels[$prev])) {	1✔
184	if ($next === 'r') {	1✔
185	return isset($this->before_r[$ch]) ? self::Here : self::After;	1✔
186
187	} elseif ($next === 'l') {	1✔
188	return isset($this->before_l[$ch]) ? self::Here : self::After;	1✔
189
190	} elseif ($next === 'h') { // CH	1✔
191	return isset($this->before_h[$ch])	1✔
192	? self::Dont	1✔
193	: self::After;	1✔
194	}
195
196	return self::After;	1✔
197	}
198
199	return self::Dont;	1✔
200
201	} elseif (($ch === 'u') && isset($this->doubleVowels[$prev])) {	1✔
202	return self::After;	×
203
204	} elseif (isset($this->vowels[$ch], $this->vowels[$prev])) {	1✔
205	return self::Here;	1✔
206	}
207
208	return self::Dont; // Do not hyphenate	1✔
209	}
210	}

dg / texy / 21501721037

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous